github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2026-03-22 13:47:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Replace environment variables with configuration file (#339)

Browse Source 
* Replace environment variables with configuration file

* Add config.toml to .gitignore

* Remove unused os imports

* Update README.md

* Update README.md

* Update README.md

* Fix merge conflict

* Fallback to environment variables

* Use template file for config.toml

* Update config.toml.template

* Update config.toml.template

---------

Co-authored-by: Robert Brennan <accounts@rbren.io>
This commit is contained in:
Jim Su
2024-03-29 15:26:20 -04:00
committed by GitHub
parent b443c0af29
commit b1b96df8a8
11 changed files with 95 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
README.md
View File

@@ -26,51 +26,58 @@ First, make sure Docker is running:
```bash
docker ps # this should exit successfully
```
Then pull our latest image [here](https://github.com/opendevin/OpenDevin/pkgs/container/sandbox)
```bash
docker pull ghcr.io/opendevin/sandbox:v0.1
```
Then copy `config.toml.template` to `config.toml`. Add an API key to `config.toml`.
(See below for how to use different models.)
```toml
OPENAI_API_KEY="..."
WORKSPACE_DIR="..."
```
Next, start the backend.
We manage python packages and the virtual environment with `pipenv`.
Make sure python >= 3.10.
Make sure you have python >= 3.10.
```bash
python -m pip install pipenv
pipenv install -v
pipenv shell
export OPENAI_API_KEY="..."
export WORKSPACE_DIR="/path/to/your/project"
python -m pip install -r requirements.txt
uvicorn opendevin.server.listen:app --port 3000
```
Then in a second terminal:
Then, in a second terminal, start the frontend:
```bash
cd frontend
npm install
npm start
```
The virtual environment is now activated and you should see `(OpenDevin)` in front of your cmdline prompt.
### Picking a Model
We use LiteLLM, so you can run OpenDevin with any foundation model, including OpenAI, Claude, and Gemini.
LiteLLM has a [full list of providers](https://docs.litellm.ai/docs/providers).
To change the model, set the `LLM_MODEL` and `LLM_API_KEY` environment variables.
To change the model, set the `LLM_MODEL` and `LLM_API_KEY` in `config.toml`.
For example, to run Claude:
```bash
export LLM_API_KEY="your-api-key"
export LLM_MODEL="claude-3-opus-20240229"
```toml
LLM_API_KEY="your-api-key"
LLM_MODEL="claude-3-opus-20240229"
```
You can also set the base URL for local/custom models:
```bash
export LLM_BASE_URL="https://localhost:3000"
```toml
LLM_BASE_URL="https://localhost:3000"
```
And you can customize which embeddings are used for the vector database storage:
```bash
export LLM_EMBEDDING_MODEL="llama2" # can be "llama2", "openai", "azureopenai", or "local"
```toml
LLM_EMBEDDING_MODEL="llama2" # can be "llama2", "openai", "azureopenai", or "local"
```
### Running the app